tag_along 0.0.1 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bb501613369741434e9f949ebeba6d1b6867db51
-  data.tar.gz: 82b99ef0fb1c3c543ac5ffa2425abd61024b59d9
+  metadata.gz: 391d3d4d89b92c4d71b051eb6545a485e4210669
+  data.tar.gz: 7356ca9775ccbbce9fce5c2078669994dc5212f2
 SHA512:
-  metadata.gz: 08ceb49d3503b05df762286a6f770d6124912b1d607eb95d7605e73d6aae61d162e5d94961a3a03588e4d8788f148335b0c17c2997b9d71735d603b3d3314be3
-  data.tar.gz: 0380c0290c379b3d69da2c640c557a11b34122d634514c2e9c7e91f2791054a5ff275bbe87064f55523817c56be4a9e2f0bdbc4908a44d76c2e95eba4307fabf
+  metadata.gz: bff906e414af8b88c001e8f532421aa6850744982489f1fbaa59108fe453642963779ebb4f1902ae7ad050258201e11541469f229c2820c1eeb7a93c65c19918
+  data.tar.gz: 4edd2b7e8856823343b586dc826ca8c8850ea597daf89d27730a09a622386e6c59bb93a14c7319c8f268f0a042195c3c186514a051824def5d115f9d83d04378

data/.gitignore

@@ -15,3 +15,4 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+bin

data/.ruby-version

@@ -0,0 +1 @@
+2.0.0-p247

data/.travis.yml

@@ -0,0 +1,7 @@
+rvm:
+  - 1.9.3
+  - 2.0.0
+bundler_args: --without development
+branches:
+  only:
+      - master

data/CHANGELOG

@@ -0,0 +1,6 @@
+0.6.1 -- fixed a bug which would crash the gem if an object without
+         item_string is entered
+
+0.6.0 -- first functional release, not tested in production
+
+0.0.1 -- initial unonfunctional placeholder

data/Gemfile

@@ -1,4 +1,17 @@
 source 'https://rubygems.org'
 
-# Specify your gem's dependencies in tag_along.gemspec
-gemspec
+gem 'json', '~> 1.7'
+
+group :development do
+  gem 'bundler', '~> 1.3'
+  gem 'debugger','~> 1.6'
+end
+
+group :test do
+  gem 'rake', '~> 10.1'
+  gem 'rspec', '~> 2.14'
+  gem 'rr', '~> 1.1'
+  gem 'coveralls', '~> 0.6'
+end
+  
+

data/README.md

@@ -1,12 +1,21 @@
 TagAlong
 ========
 
+[![Gem Version][1]][2]
+[![Continuous Integration Status][3]][4]
+[![Coverage Status][5]][6]
+[![CodePolice][7]][8]
+[![Dependency Status][9]][10]
+
 A user who runs a search tool against a text would find 
 multiple text fragments corresponding to the search.
 These fragments can be found again by storing their 
 start and end offsets. This gem places arbitrary
 markup tags surrounding the fragments.
 
+Gem works with UTF-8 and ASCII7 texts. It is quite fast and allows to tag
+4MB of text in one second on 2.7GHz processor.
+
 Installation
 ------------
 
@@ -25,12 +34,54 @@ Or install it yourself as:
 Usage
 -----
 
-To add tags to a text:
+For example you want to tag days of week from a text:
 
-    tg = TagAlong.new(some_text)
-    offsets = [[2, 5], [9, 22], [33, 35]]
-    tg.tag('<my_tag>', '</my_tag>', offsets)
+    text = "There's Sunday and there's Monday"
+
+To add tags to a text:
 
+    offsets = [[8,13], [27,32]]
+    tg = TagAlong.new(text, offsets)
+    
+    tg.tag('<my_tag>', '</my_tag>')
+    puts tg.tagged_text
+    # There's <my_tag>Sunday</my_tag> and there's <my_tag>Monday</my_tag>
+    
+    tg.tag('<em>', '</em>')
+    puts tg.tagged_text
+    # There's <em>Sunday</em> and there's <em>Monday</em>
+
+Notice that you can retag the text as many times as you want.
+
+### Offsets
+  
+To prepare offsets from an arbitrary object:
+    
+    # Array of arrays
+    my_ary = [[8,13], [27,32]]
+    offsets = TagAlong::Offsets.new(my_ary)
+
+    # Array of hashes
+    my_hash = [{ start: 8, end:13 }, { start:27, end:32 }]
+    offsets = TagAlong::Offsets.new(my_hash,
+                                    offset_start: 'start'
+                                    offset_end: 'end')
+    or
+    offsets = TagAlong::Offsets.new(my_hash,
+                                    offset_start: :start,
+                                    offset_end: :end)
+
+    # Array of objects
+    require 'ostruct'
+    my_obj = [OpenStruct.new(s: 8, e: 13), OpenStruct.new(s: 27, e: 32)]
+    offsets = TagAlong::Offsets.new(my_obj,
+                                    offset_start: :s,
+                                    offset_end: :e)
+
+In all cases you can instantiate TagAlong with resulting offsets:
+
+    tg = TagAlong.new(text, offsets)
+    tg.tag('|hi|', '|bye|')
 
 Contributing
 ------------
@@ -44,9 +95,19 @@ Contributing
 Copyright
 ---------
 
-Authors: [Dmitry Mozzherin][1], 
+Authors: [Dmitry Mozzherin][11] 
 
 Copyright (c) 2013 Marine Biological Laboratory. See LICENSE for
 further details.
 
-[1]: https://github.com/dimus
+[1]: https://badge.fury.io/rb/tag_along.png
+[2]: http://badge.fury.io/rb/tag_along
+[3]: https://secure.travis-ci.org/GlobalNamesArchitecture/tag_along.png
+[4]: http://travis-ci.org/GlobalNamesArchitecture/tag_along
+[5]: https://coveralls.io/repos/GlobalNamesArchitecture/tag_along/badge.png?branch=master
+[6]: https://coveralls.io/r/GlobalNamesArchitecture/tag_along?branch=master
+[7]: https://codeclimate.com/github/GlobalNamesArchitecture/tag_along.png
+[8]: https://codeclimate.com/github/GlobalNamesArchitecture/tag_along
+[9]: https://gemnasium.com/GlobalNamesArchitecture/tag_along.png
+[10]: https://gemnasium.com/GlobalNamesArchitecture/tag_along
+[11]: https://github.com/dimus

data/Rakefile

@@ -1 +1,20 @@
-require "bundler/gem_tasks"
+require 'bundler'
+require 'bundler/gem_tasks'
+require 'rspec/core'
+require 'rspec/core/rake_task'
+
+Bundler::GemHelper.install_tasks
+
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts 'Run `bundle install` to install missing gems'
+  exit e.status_code
+end
+
+task :default => :spec
+
+RSpec::Core::RakeTask.new do |t|
+  t.pattern = 'spec/**/*spec.rb'
+end

data/lib/tag_along/offsets.rb

@@ -0,0 +1,78 @@
+class TagAlong
+
+  class Offsets
+    include Enumerable
+
+    def initialize(offsets, opts = {})
+
+      @offsets      = offsets
+      @offset_start = (opts[:offset_start] || 'offset_start').to_sym
+      @offset_end   = (opts[:offset_end]   || 'offset_end').to_sym
+      @item_string   = (opts[:item_string]  || 'item_string').to_sym
+      
+      item = @offsets.first
+      if item.is_a?(Array)
+        process_array
+      elsif item.is_a?(Hash)
+        process_hash
+      else 
+        process_obj
+      end
+    end
+
+    def each(&block)
+      @offsets.each do |o|
+        block.call(o)
+      end
+    end
+
+    private
+
+    def process_array
+      @offsets = @offsets.map do |o|
+        offset_start = o[0]
+        offset_end = o[1]
+        item_string = o[2]
+        instantiate(offset_start, offset_end, item_string) 
+      end
+    end
+
+    def process_hash
+      @offsets.each { |h| symbolize_keys(h) }
+      @offsets = @offsets.map do |o|
+        instantiate(o[@offset_start], o[@offset_end], o[@item_string]) 
+      end
+    end
+
+    def process_obj
+      @offsets = @offsets.map do |o|
+        item_string = o.respond_to?(@item_string) ? 
+          o.send(@item_string) :
+          nil
+        instantiate(o.send(@offset_start), 
+                    o.send(@offset_end), 
+                    item_string) 
+      end
+    end
+    
+    def instantiate(offset_start, offset_end, item_string)
+      OpenStruct.new(offset_start: to_int(offset_start),
+                     offset_end:   to_int(offset_end),
+                     item_string:  item_string)
+    end
+
+    def to_int(val)
+      int = val.to_i
+      raise TypeError.new('Offsets must be integers') if int.to_s != val.to_s
+      int
+    end
+
+    def symbolize_keys(a_hash)
+      a_hash.keys.each do |key|
+        a_hash[(key.to_sym rescue key) || key] = a_hash.delete(key)
+      end
+    end
+    
+  end
+
+end

data/lib/tag_along/version.rb

@@ -1,3 +1,3 @@
-module TagAlong
-  VERSION = "0.0.1"
+class TagAlong
+  VERSION = '0.6.1'
 end

data/lib/tag_along.rb

@@ -1,5 +1,61 @@
-require "tag_along/version"
+require 'ostruct'
+require 'tag_along/version'
+require 'tag_along/offsets'
+
+class TagAlong
+
+  attr :text, :tagged_text
+
+  def self.version
+    VERSION
+  end
+
+  def initialize(text, offsets)
+    @offsets = offsets.is_a?(Offsets) ? offsets : Offsets.new(offsets)
+    @text = text
+    @split_text = nil
+    @tagged_text = nil
+    split_text
+  end
+
+  def tag(open_tag, close_tag)
+    @tagged_text = @split_text.inject([]) do |res, t|
+      if t[:tagged]
+        [open_tag, t[:text], close_tag].each { |text| res << text }
+      else
+        res << t[:text]
+      end
+      res
+    end.join('')
+  end
+
+  private
+
+  def split_text
+    return  if @split_text
+    
+    text_ary = @text.unpack('U*')
+    cursor = 0
+    fragment = []
+    res = []
+    
+    @offsets.each do |item|
+      chars_num = item.offset_start - cursor
+      chars_num.times { fragment << text_ary.shift }
+      res << { tagged: false, text: fragment }
+      fragment = []
+      cursor = item.offset_start
+      chars_num = item.offset_end + 1 - cursor
+      chars_num.times { fragment << text_ary.shift }
+      res << { tagged: true, text: fragment }
+      fragment = []
+      cursor = item.offset_end + 1
+    end
+
+    res.each do |r|
+      r[:text] = r[:text].pack('U*')
+    end
+    @split_text = res
+  end
 
-module TagAlong
-  # Your code goes here...
 end

data/spec/files/spec_data.json

@@ -0,0 +1,407 @@
+{
+  "token_url": "http://gnrd.globalnames.org/name_finder.json?token=Row8ZZJSTsuwJxhQtgha9A",
+  "input_url": null,
+  "file": "Embryology 1939_15B.tiff",
+  "status": 200,
+  "engines": [
+    "TaxonFinder",
+    "NetiNeti"
+  ],
+  "unique": false,
+  "verbatim": true,
+  "english": true,
+  "execution_time": {
+    "find_names_duration": 0.237166328,
+    "resolve_names_duration": 1.956796471,
+    "total_duration": 23.716051434
+  },
+  "agent": "",
+  "created": "2013-06-19T15:22:01-04:00",
+  "total": 11,
+  "names": [
+    {
+      "verbatim": "Pundulus",
+      "scientificName": "Pundulus",
+      "offsetStart": 61,
+      "offsetEnd": 68,
+      "identifiedName": "Pundulus"
+    },
+    {
+      "verbatim": "Lebistes reticulatus",
+      "scientificName": "Lebistes reticulatus",
+      "offsetStart": 866,
+      "offsetEnd": 885,
+      "identifiedName": "Lebistes reticulatus"
+    },
+    {
+      "verbatim": "Cottus",
+      "scientificName": "Cottus",
+      "offsetStart": 955,
+      "offsetEnd": 960,
+      "identifiedName": "Cottus"
+    },
+    {
+      "verbatim": "Entosphenus wilderi",
+      "scientificName": "Entosphenus wilderi",
+      "offsetStart": 1085,
+      "offsetEnd": 1103,
+      "identifiedName": "Entosphenus wilderi"
+    },
+    {
+      "verbatim": "Fundulus",
+      "scientificName": "Fundulus",
+      "offsetStart": 1347,
+      "offsetEnd": 1354,
+      "identifiedName": "Fundulus"
+    },
+    {
+      "verbatim": "Fundulus heteroclitus",
+      "scientificName": "Fundulus heteroclitus",
+      "offsetStart": 1604,
+      "offsetEnd": 1624,
+      "identifiedName": "Fundulus heteroclitus"
+    },
+    {
+      "verbatim": "Nouveaux essais",
+      "scientificName": "Nouveaux essais",
+      "offsetStart": 1857,
+      "offsetEnd": 1871,
+      "identifiedName": "Nouveaux essais"
+    },
+    {
+      "verbatim": "Acipenser",
+      "scientificName": "Acipenser",
+      "offsetStart": 2137,
+      "offsetEnd": 2145,
+      "identifiedName": "Acipenser"
+    },
+    {
+      "verbatim": "Acipenser guldenstadtii",
+      "scientificName": "Acipenser guldenstadtii",
+      "offsetStart": 2183,
+      "offsetEnd": 2205,
+      "identifiedName": "Acipenser guldenstadtii"
+    },
+    {
+      "verbatim": "Acipenser stellatus",
+      "scientificName": "Acipenser stellatus",
+      "offsetStart": 2211,
+      "offsetEnd": 2229,
+      "identifiedName": "Acipenser stellatus"
+    },
+    {
+      "verbatim": "Fundulus heteroclitus",
+      "scientificName": "Fundulus heteroclitus",
+      "offsetStart": 2462,
+      "offsetEnd": 2482,
+      "identifiedName": "Fundulus heteroclitus"
+    }
+  ],
+  "content": "1959 \nNewman H. H. Spawmin behavior and sexual dimorphism of Pundulus\n9 5 QS\nheteroclitus and allied fish. Biol. Bull. 12, 1907.\nIV. CIRGULATORY SYSTEM\nP. B. Functional reactions in the embryonic heart accom~\npanying the ingrowth and development of the vagus\ninnervation. Jour. Exp. Zool. 58, 1951.\nBrinley, P. J. A Physiological study of the innervation of the\nheart of fish embryos. Physiol. Zool. 5, 1952.\nReagan, F, P. Experimental studies in the origin of the vascular\nendothelium and of Am. Jour, Anat.\n21, 1917. \nShearer, E. M. Studies on the embryology of the circulation in\nfishes, 1. and ll. Am. Jour. Anat. 46, 1950.\nStockard, C. R. An experimental analysis of the origin of blood\nand vascular endothelium Mem. Wist. Inst. Anat.\nBiol. No. 7, 1915. also Am. Jour, Anat. 18, 1915.\nV. GERM CELLS\nGoodrich, H. B., et al. Germ cells and sex differentiation in\nLebistes reticulatus. Biol. Bull. 67, 1954.\nMann, H. W. The history of the germ cells of Cottus Baerdii. Gerard\nJour. Morph. Physiol. 45, 1927.\nokkelberg, Peter The early history of the germ cells in the brook\nlamprey, Entosphenus wilderi (Gage) up to and in~\ncluding the period of sex differentiation. Jour.\nMorph. 55, 1921. (This paper has a complete bib-\nliography of work on germ cells in other groups.)\nTichards, A. and Thompson, James I., Migration with primary sex\ncells of Fundulus hetercclitus Biol. Bull. 40, 1921.\nWolf, L. E. The history of the germ cells in the viviparous\n1 teleost PPlatypoecilus maculatus. Jour. Morph. and\nPhysiol. 52, 1951.\n1 VI. EXPERIMENTAL WORK.\nAmberson, W. R, and F. B. The respiratory metabolism\nof Fundulus heteroclitus during embryonic develop-\nmental Jour. Cell. and Comp. Physiol. 2, 1955.\nP. B. The embryonic origin of function in the pronephros\nthrough differentiation and paren~chyma-vascular\nassociation. Amer. Jour. Anat. 51, 1952.\nBatallion, Nouveaux essais de Parthenogenere experimentale chez les\nvertibres infesienes Arch. Ent. Mech. 18, 1904.\nClapp, C. M. The relation of the axis of the embryo to the first\ncleavage plane. Biol Lect. M. B. L. 1898.\nFilatow, D. Entwicklungsmechanishhe Untersuchungen an Embryonen\nvon Acipenser guldenstadtti and Acipenbryonen von\nAcipenser guldenstadtii und Acipenser stellatus.\nArch. Ent. Mech. 122, 1950.\nHinriChS,.M. A. and Genther 1. T. Ultraviolet radiation and the\nproduction of twins and double monsters. Physiol.\niZool. 4, 1951.\nHeadley, L. 0n the localization of developmental potencies in\nembryo of Fundulus heteroclitus Jour. Exp. Zool.\n52, 1928.\n\n",
+  "data_sources": [
+
+  ],
+  "context": null,
+  "resolved_names": [
+    {
+      "supplied_name_string": "Pundulus",
+      "results": [
+        null
+      ],
+      "preferred_results": [
+
+      ],
+      "data_sources_number": 0,
+      "in_curated_sources": false
+    },
+    {
+      "supplied_name_string": "Lebistes reticulatus",
+      "results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "3564821e-720d-587c-96d7-7e29612a81ad",
+          "name_string": "Lebistes reticulatus",
+          "canonical_form": "Lebistes reticulatus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "37270453",
+          "local_id": "11081658",
+          "url": "http://eol.org/pages/11081658",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "3564821e-720d-587c-96d7-7e29612a81ad",
+          "name_string": "Lebistes reticulatus",
+          "canonical_form": "Lebistes reticulatus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "37270453",
+          "local_id": "11081658",
+          "url": "http://eol.org/pages/11081658",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "data_sources_number": 11,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Cottus",
+      "results": [
+        {
+          "data_source_id": 1,
+          "data_source_title": "Catalogue of Life",
+          "gni_uuid": "ee98e65c-3d7b-5317-91e8-eb543255e7ba",
+          "name_string": "Cottus",
+          "canonical_form": "Cottus",
+          "classification_path": "Animalia|Chordata|Actinopterygii|Scorpaeniformes|Cottidae|Cottus",
+          "classification_path_ranks": "kingdom|phylum|class|order|family|genus",
+          "classification_path_ids": "2362377|2362754|2365430|2365507|2365562|2396188",
+          "taxon_id": "2396188",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "ee98e65c-3d7b-5317-91e8-eb543255e7ba",
+          "name_string": "Cottus",
+          "canonical_form": "Cottus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "37305832",
+          "local_id": "204556",
+          "url": "http://eol.org/pages/204556",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "data_sources_number": 19,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Entosphenus wilderi",
+      "results": [
+        {
+          "data_source_id": 168,
+          "data_source_title": "Index to Organism Names",
+          "gni_uuid": "11c30211-b0b8-5927-903e-1f959cd6173b",
+          "name_string": "Entosphenus wilderi",
+          "canonical_form": "Entosphenus wilderi",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "128746584",
+          "url": "http://www.organismnames.com/details.htm?lsid=3414383",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "preferred_results": [
+
+      ],
+      "data_sources_number": 1,
+      "in_curated_sources": false
+    },
+    {
+      "supplied_name_string": "Fundulus",
+      "results": [
+        {
+          "data_source_id": 1,
+          "data_source_title": "Catalogue of Life",
+          "gni_uuid": "849efb3e-564d-5bed-b388-d2abd1e89de0",
+          "name_string": "Fundulus",
+          "canonical_form": "Fundulus",
+          "classification_path": "Animalia|Chordata|Actinopterygii|Cyprinodontiformes|Fundulidae|Fundulus",
+          "classification_path_ranks": "kingdom|phylum|class|order|family|genus",
+          "classification_path_ids": "2362377|2362754|2365430|2369356|2369363|2396458",
+          "taxon_id": "2396458",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "849efb3e-564d-5bed-b388-d2abd1e89de0",
+          "name_string": "Fundulus",
+          "canonical_form": "Fundulus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "37305680",
+          "local_id": "207614",
+          "url": "http://eol.org/pages/207614",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "data_sources_number": 16,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Fundulus heteroclitus",
+      "results": [
+        {
+          "data_source_id": 4,
+          "data_source_title": "NCBI",
+          "gni_uuid": "b4e4dfca-4136-5fc1-8688-53af51190898",
+          "name_string": "Fundulus heteroclitus",
+          "canonical_form": "Fundulus heteroclitus",
+          "classification_path": "|Eukaryota|Opisthokonta|Metazoa|Eumetazoa|Bilateria|Coelomata|Deuterostomia|Chordata|Craniata|Vertebrata|Gnathostomata|Teleostomi|Euteleostomi|Actinopterygii|Actinopteri|Neopterygii|Teleostei|Elopocephala|Clupeocephala|Euteleostei|Neognathi|Neoteleostei|Eurypterygii|Ctenosquamata|Acanthomorpha|Euacanthomorpha|Holacanthopterygii|Acanthopterygii|Euacanthopterygii|Percomorpha|Smegmamorpha|Atherinomorpha|Cyprinodontiformes|Cyprinodontoidei|Fundulidae|Fundulus|Fundulus heteroclitus",
+          "classification_path_ranks": "|superkingdom||kingdom|||||phylum|subphylum||superclass|||class||||||||||||||superorder|||||order|suborder|family|genus|species",
+          "classification_path_ids": "131567|2759|33154|33208|6072|33213|33316|33511|7711|89593|7742|7776|117570|117571|7898|186623|41665|32443|186624|186625|32447|186839|123365|123366|123367|123368|123369|123370|32455|129947|32485|129949|32456|28738|8087|28756|8077|8078",
+          "taxon_id": "8078",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "b4e4dfca-4136-5fc1-8688-53af51190898",
+          "name_string": "Fundulus heteroclitus",
+          "canonical_form": "Fundulus heteroclitus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "39163140",
+          "local_id": "1157172",
+          "url": "http://eol.org/pages/1157172",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "data_sources_number": 15,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Nouveaux essais"
+    },
+    {
+      "supplied_name_string": "Acipenser",
+      "results": [
+        {
+          "data_source_id": 1,
+          "data_source_title": "Catalogue of Life",
+          "gni_uuid": "0801dea4-b087-5845-b4f3-e27adeb5eef7",
+          "name_string": "Acipenser",
+          "canonical_form": "Acipenser",
+          "classification_path": "Animalia|Chordata|Actinopterygii|Acipenseriformes|Acipenseridae|Acipenser",
+          "classification_path_ranks": "kingdom|phylum|class|order|family|genus",
+          "classification_path_ids": "2362377|2362754|2365430|2371893|2371895|2395796",
+          "taxon_id": "2395796",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "0801dea4-b087-5845-b4f3-e27adeb5eef7",
+          "name_string": "Acipenser",
+          "canonical_form": "Acipenser",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "20627458",
+          "local_id": "15048",
+          "url": "http://eol.org/pages/15048",
+          "match_type": 1,
+          "prescore": "1|0|0",
+          "score": 0.75
+        }
+      ],
+      "data_sources_number": 19,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Acipenser guldenstadtii",
+      "results": [
+        {
+          "data_source_id": 168,
+          "data_source_title": "Index to Organism Names",
+          "gni_uuid": "4bd1443b-c862-5ac3-849b-18d481af6a4e",
+          "name_string": "Acipenser guldenstadtii",
+          "canonical_form": "Acipenser guldenstadtii",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "126471337",
+          "url": "http://www.organismnames.com/details.htm?lsid=960481",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "preferred_results": [
+
+      ],
+      "data_sources_number": 3,
+      "in_curated_sources": true
+    },
+    {
+      "supplied_name_string": "Acipenser stellatus",
+      "results": [
+        {
+          "data_source_id": 4,
+          "data_source_title": "NCBI",
+          "gni_uuid": "35353b10-cb9b-50dd-929c-934c4e6ff172",
+          "name_string": "Acipenser stellatus",
+          "canonical_form": "Acipenser stellatus",
+          "classification_path": "|Eukaryota|Opisthokonta|Metazoa|Eumetazoa|Bilateria|Coelomata|Deuterostomia|Chordata|Craniata|Vertebrata|Gnathostomata|Teleostomi|Euteleostomi|Actinopterygii|Actinopteri|Chondrostei|Acipenseriformes|Acipenseroidei|Acipenseridae|Acipenserinae|Acipenserini|Acipenser|Acipenser stellatus",
+          "classification_path_ranks": "|superkingdom||kingdom|||||phylum|subphylum||superclass|||class|||order|suborder|family|subfamily|tribe|genus|species",
+          "classification_path_ids": "131567|2759|33154|33208|6072|33213|33316|33511|7711|89593|7742|7776|117570|117571|7898|186623|32440|7899|186622|7900|124129|124130|7901|7903",
+          "taxon_id": "7903",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "preferred_results": [
+        {
+          "data_source_id": 12,
+          "data_source_title": "EOL",
+          "gni_uuid": "35353b10-cb9b-50dd-929c-934c4e6ff172",
+          "name_string": "Acipenser stellatus",
+          "canonical_form": "Acipenser stellatus",
+          "classification_path": "",
+          "classification_path_ranks": "",
+          "classification_path_ids": "",
+          "taxon_id": "35677530",
+          "local_id": "206889",
+          "url": "http://eol.org/pages/206889",
+          "match_type": 1,
+          "prescore": "3|0|0",
+          "score": 0.988
+        }
+      ],
+      "data_sources_number": 23,
+      "in_curated_sources": true
+    }
+  ]
+}

data/spec/spec_helper.rb

@@ -0,0 +1,33 @@
+require 'coveralls'
+Coveralls.wear!
+
+require 'json'
+require 'ostruct'
+require_relative '../lib/tag_along'
+
+RSpec.configure do |c|
+  c.mock_with :rr
+end
+
+module TagAlongSpec
+  def self.process_spec_data(dir)
+    data = open(File.join(dir, 'spec_data.json')).read
+    data = JSON.parse(data, symbolize_names: true)
+    text = data[:content]
+    offset_hash = data[:names]
+    offset_obj = offset_hash.map do |h| 
+      OpenStruct.new(name: h[:verbatim],
+                     start: h[:offsetStart],
+                     end: h[:offsetEnd])
+    end
+    offset_ary = offset_obj.map { |h| [h.start, h.end] }
+    [text, offset_ary, offset_hash, offset_obj]
+  end
+end
+
+unless defined?(SPEC_VARS)
+  FILES_DIR = File.expand_path(File.join(File.dirname(__FILE__), 'files'))
+  TEXT, OFFSETS_ARY, OFFSETS_HASH, OFFSETS_OBJ = 
+    TagAlongSpec.process_spec_data(FILES_DIR)
+  SPEC_VARS = true
+end

data/spec/tag_along/offsets_spec.rb

@@ -0,0 +1,61 @@
+require_relative '../spec_helper'
+
+describe TagAlong::Offsets do
+
+  it 'should initialize' do
+    o = TagAlong::Offsets.new(OFFSETS_ARY)
+    o.is_a?(TagAlong::Offsets).should be_true
+  end
+
+  it 'should process arrays' do
+    o = TagAlong::Offsets.new(OFFSETS_ARY)
+    o.is_a?(TagAlong::Offsets).should be_true
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should be_nil
+    ary_with_item = OFFSETS_HASH.map do |h| 
+      [h[:offsetStart], h[:offsetEnd], h[:verbatim]]
+    end
+    o = TagAlong::Offsets.new(ary_with_item)
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should == 'Pundulus'
+    -> { TagAlong::Offsets.new([['a','b']]) }.should 
+      raise_error(TypeError, 'Offsets must be integers') 
+  end
+
+  it 'should process hash' do
+    o = TagAlong::Offsets.new(OFFSETS_HASH, 
+                              offset_start: :offsetStart,
+                              offset_end: :offsetEnd)
+    o.is_a?(TagAlong::Offsets).should be_true
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should be_nil
+    o = TagAlong::Offsets.new(OFFSETS_HASH, 
+                              offset_start: 'offsetStart',
+                              offset_end: 'offsetEnd',
+                              item_string: 'verbatim')
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should == 'Pundulus'
+  end
+
+  it 'should process object' do
+    o = TagAlong::Offsets.new(OFFSETS_OBJ, 
+                              offset_start: :start,
+                              offset_end: :end)
+    o.is_a?(TagAlong::Offsets).should be_true
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should be_nil
+    o = TagAlong::Offsets.new(OFFSETS_OBJ, 
+                              offset_start: :start,
+                              offset_end: :end,
+                              item_string: 'name')
+    o.is_a?(TagAlong::Offsets).should be_true
+    o.first.offset_start.should == 61
+    o.first.offset_end.should == 68
+    o.first.item_string.should == 'Pundulus'
+  end
+end

data/spec/tag_along_spec.rb

@@ -0,0 +1,33 @@
+require 'spec_helper'
+
+describe TagAlong do
+  it 'should have version' do
+    TagAlong.version.should =~ /^[\d]+\.[\d]+.[\d]+$/
+  end
+
+  it 'should initialize' do
+    tg = TagAlong.new(TEXT, OFFSETS_ARY)
+    tg.is_a?(TagAlong).should be_true
+    tg.text.should == TEXT
+    tg.tagged_text.should be_nil
+  end
+
+  it 'should tag' do
+    tg = TagAlong.new(TEXT, OFFSETS_ARY)
+    tagged_text = tg.tag('<my_tag>', '</my_tag>')
+    tg.tagged_text.should == tagged_text
+    tg.tagged_text.should include('<my_tag>Lebistes reticulatus</my_tag>')
+    tagged_text = tg.tag('<another_tag>', '</another_tag>')
+    tg.tagged_text.should == tagged_text
+    tg.tagged_text.should 
+      include('<another_tag>Lebistes reticulatus</another_tag>')
+  end
+
+  it 'should tag' do
+    text = 'There\'s Sunday and there\'s Monday'
+    offsets = [[8,13], [27,32]]
+    tg = TagAlong.new(text, offsets)
+    tg.tag('<em>', '</em>').should == 
+      %q{There's <em>Sunday</em> and there's <em>Monday</em>}
+  end
+end

data/tag_along.gemspec

@@ -3,26 +3,22 @@ lib = File.expand_path('../lib', __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'tag_along/version'
 
-Gem::Specification.new do |spec|
-  spec.name          = "tag_along"
-  spec.version       = TagAlong::VERSION
-  spec.authors       = ["Dmitry Mozzherin"]
-  spec.email         = ["dmozzherin@gmail.com"]
-  spec.description   = %q{Tags a text with arbitrary tags
+Gem::Specification.new do |sp|
+  sp.name          = 'tag_along'
+  sp.version       = TagAlong::VERSION
+  sp.authors       = ['Dmitry Mozzherin']
+  sp.email         = ['dmozzherin@gmail.com']
+  sp.description   = %q{Tags a text with arbitrary tags
                           based on array of start/end offsets}
-  spec.summary       = %q{A user who runs a search tool on a text would find 
+  sp.summary       = %q{A user who runs a search tool on a text would find 
                           multiple text fragments corresponding to the search.
                           These fragments can be found again by storing their 
                           start and end offsets. This gem places arbitrary
                           markup tags surrounding the fragments.}
-  spec.homepage      = ""
-  spec.license       = "MIT"
+  sp.homepage      = 'https://github.com/GlobalNamesArchitecture/tag_along'
+  sp.license       = 'MIT'
 
-  spec.files         = `git ls-files`.split($/)
-  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
-  spec.require_paths = ["lib"]
-
-  spec.add_development_dependency "bundler", "~> 1.3"
-  spec.add_development_dependency "rake"
+  sp.files         = `git ls-files`.split($/)
+  sp.test_files    = sp.files.grep(%r{^(spec|features)/})
+  sp.require_paths = ['lib']
 end

metadata

@@ -1,43 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: tag_along
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.6.1
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-31 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.3'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.3'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
+date: 2013-09-03 00:00:00.000000000 Z
+dependencies: []
 description: |-
   Tags a text with arbitrary tags
                             based on array of start/end offsets
@@ -48,14 +20,22 @@ extensions: []
 extra_rdoc_files: []
 files:
 - .gitignore
+- .ruby-version
+- .travis.yml
+- CHANGELOG
 - Gemfile
 - LICENSE.txt
 - README.md
 - Rakefile
 - lib/tag_along.rb
+- lib/tag_along/offsets.rb
 - lib/tag_along/version.rb
+- spec/files/spec_data.json
+- spec/spec_helper.rb
+- spec/tag_along/offsets_spec.rb
+- spec/tag_along_spec.rb
 - tag_along.gemspec
-homepage: ''
+homepage: https://github.com/GlobalNamesArchitecture/tag_along
 licenses:
 - MIT
 metadata: {}
@@ -81,4 +61,8 @@ specification_version: 4
 summary: A user who runs a search tool on a text would find  multiple text fragments
   corresponding to the search. These fragments can be found again by storing their  start
   and end offsets. This gem places arbitrary markup tags surrounding the fragments.
-test_files: []
+test_files:
+- spec/files/spec_data.json
+- spec/spec_helper.rb
+- spec/tag_along/offsets_spec.rb
+- spec/tag_along_spec.rb